US8862922B2 - Data center power adjustment - Google Patents

Data center power adjustment Download PDF

Info

Publication number
US8862922B2
US8862922B2 US12687241 US68724110A US8862922B2 US 8862922 B2 US8862922 B2 US 8862922B2 US 12687241 US12687241 US 12687241 US 68724110 A US68724110 A US 68724110A US 8862922 B2 US8862922 B2 US 8862922B2
Authority
US
Grant status
Grant
Patent type
Prior art keywords
virtual machine
power consumption
power
predetermined limit
data center
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related, expires
Application number
US12687241
Other versions
US20110173465A1 (en )
Inventor
Jason B. Akers
Ross B. Clay
Perry L. Jones
Ryan A. Holt
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/14Error detection or correction of the data by redundancy in operation
    • G06F11/1402Saving, restoring, recovering or retrying
    • G06F11/1415Saving, restoring, recovering or retrying at system level
    • G06F11/1417Boot up procedures
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 – G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power Management, i.e. event-based initiation of power-saving mode
    • G06F1/3206Monitoring a parameter, a device or an event triggering a change in power modality
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 – G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power Management, i.e. event-based initiation of power-saving mode
    • G06F1/3234Action, measure or step performed to reduce power consumption
    • G06F1/3287Power saving by switching off individual functional units in a computer system, i.e. selective power distribution
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 – G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power Management, i.e. event-based initiation of power-saving mode
    • G06F1/3234Action, measure or step performed to reduce power consumption
    • G06F1/329Power saving by task scheduling
    • HELECTRICITY
    • H05ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
    • H05KPRINTED CIRCUITS; CASINGS OR CONSTRUCTIONAL DETAILS OF ELECTRIC APPARATUS; MANUFACTURE OF ASSEMBLAGES OF ELECTRICAL COMPONENTS
    • H05K7/00Constructional details common to different types of electric apparatus
    • H05K7/14Mounting supporting structure in casing or on frame or rack
    • H05K7/1485Servers; Data center rooms, e.g. 19-inch computer racks
    • H05K7/1498Resource management, Optimisation arrangements, e.g. configuration, identification, tracking, physical location
    • Y02B60/148
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing
    • Y02D10/10Reducing energy consumption at the single machine level, e.g. processors, personal computers, peripherals or power supply
    • Y02D10/17Power management
    • Y02D10/171Selective power distribution
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing
    • Y02D10/20Reducing energy consumption by means of multiprocessor or multiprocessing based techniques, other than acting upon the power supply
    • Y02D10/24Scheduling

Abstract

A power cap agent establishes a power cap. The power cap agent throttles a first power priority virtual machine. The power cap agent determines that the first power priority virtual machine and the additional power priority virtual machine contribute to power consumption above the power cap among the plurality of servers. The power cap agent throttles the additional power priority virtual machine, wherein the first power priority virtual machine has a first power priority lower than an additional power priority of the additional power priority virtual machine. The power cap agent determines that the first power priority virtual machine and the additional power priority virtual machine contribute to power consumption above the power cap, responsive to throttling the first power priority virtual machine and throttling the additional virtual machine.

Description

BACKGROUND OF THE INVENTION

The present invention relates generally to a computer implemented method, data processing system, and computer program product for responding to power events. More specifically, the present invention relates to responding to calls to scale up or scale down electrical power consumption by selectively increasing or reducing power to virtual partitions.

Electrical power producers respond to overall power consumed on an electrical power grid. When electrical power consumption exceeds a capacity of a grid to provide electrical power, the electrical power producers must change the distribution of electrical power to avoid failures. In the past, these changes in distribution result in the lowering of voltage in electrical power supplied to geographic areas, commonly referred to as a brownout. More drastic changes in the distribution may result in blackouts.

Datacenters are large energy consumers, and thus must often work closely with local power companies. In the event of rolling blackouts or brownouts, power companies may contact large consumers such as datacenters and demand that the datacenter administrators reduce their power consumption in order to reduce demand on the power grid.

SUMMARY OF THE INVENTION

The present invention provides a computer implemented method, data processing system, and computer program product for adjusting power consumed in a data center. A power cap agent establishes a power cap. The power cap agent throttles a first power priority virtual machine. The power cap agent determines that the first power priority virtual machine and the additional power priority virtual machine contribute to power consumption above the power cap among the plurality of servers. The power cap agent throttles the additional power priority virtual machine, wherein the first power priority virtual machine has a first power priority lower than an additional power priority of the additional power priority virtual machine. The power cap agent determines that the first power priority virtual machine and the additional power priority virtual machine contribute to power consumption above the power cap, responsive to throttling the first power priority virtual machine and throttling the additional power priority virtual machine. The power cap agent shuts down the first power priority virtual machine, responsive to a determination that the first power priority virtual machine and the additional power priority virtual machine contribute to power consumption above the power cap.

BRIEF DESCRIPTION OF THE DRAWINGS

The novel features believed characteristic of the invention are set forth in the appended claims. The invention itself, however, as well as a preferred mode of use, further objectives and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings, wherein:

FIG. 1 is a block diagram of a data processing system in accordance with an illustrative embodiment of the invention;

FIG. 2 is a block diagram of a data center in accordance with an illustrative embodiment of the invention;

FIG. 3 is a priority record data structure in accordance with an illustrative embodiment of the invention;

FIG. 4 is an additional power priority record data structure in accordance with an illustrative embodiment of the invention;

FIG. 5 is a flowchart for performing power adjustments in accordance with an illustrative embodiment of the invention; and

FIG. 6 is a flowchart for relieving power reduction in accordance with an illustrative embodiment of the invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

Illustrative embodiments of the invention provide a method, apparatus, and computer program product for dispatching workloads to servers, and optionally adjusting processor voltages and frequencies based on resource requirements including power constraints, among others. The data processing device may be a stand-alone computing device, a cluster of computing devices operating as a single system or a distributed data processing system in which multiple computing devices are utilized to perform various aspects of the present invention. Therefore, the following FIGS. 1 and 2 are provided as exemplary diagrams of data processing environments in which the invention may be implemented. FIGS. 1 and 2 are only exemplary and are not intended to assert or imply any limitation with regard to the environments in which the invention may be implemented. Many modifications to the depicted environments may be made without departing from the spirit and scope of the invention.

With reference now to the figures, and in particular with reference to FIG. 1, a block diagram of a data processing system in which the invention may be implemented is depicted. Data processing system 100 may be a symmetric multiprocessor (SMP) system including a plurality of processors 101, 102, 103, and 104 connected to system bus 105. For example, data processing system 100 may be an IBM® Power Systems™ server, a product of International Business Machines Corporation of Armonk, N.Y. Also connected to system bus 105 is memory cache 106, which provides cache memory and an interface to system memory 107. I/O bus bridge 108 is connected to system bus 105 and provides an interface to I/O bus 109. I/O bus 109 connects the I/O bus bridge 108 to a plurality of I/O devices, 110, 111, 112, and 113. Data processing system 100 may be implemented using various commercially available computer systems. For example, data processing system 100 may be implemented using IBM® Power® 595 system available from International Business Machines Corporation. It is appreciated that an I/O device can be, for example, a computer readable storage media. Computer readable storage media includes, for example, magnetic disks, optical disks, and flash memory.

Those of ordinary skill in the art will appreciate that the hardware in FIG. 1 may vary depending on the implementation. Other internal hardware or peripheral devices, such as flash memory, equivalent non-volatile memory, and the like, may be used in addition to or in place of the hardware depicted in FIG. 1. In addition, the processes of the illustrative embodiments may be applied to a multiprocessor data processing system.

In some illustrative examples, data processing system 100 may be a personal digital assistant (PDA), which is configured with flash memory to provide non-volatile memory for storing operating system files and/or user-generated data. A bus system may be comprised of one or more buses, such as a system bus, an I/O bus, and a PCI bus. Of course, the bus system may be implemented using any type of communications fabric or architecture that provides for a transfer of data between different components or devices attached to the fabric or architecture. A communication unit may include one or more devices used to transmit and receive data, such as a modem or a network adapter. A memory may be, for example, system memory 107 or a cache 106. A processing unit may include one or more processors or CPUs. The depicted example in FIG. 1 is not meant to imply architectural limitations. For example, data processing system 100 also may be a tablet computer, laptop computer, or telephone device in addition to taking the form of a PDA.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

The corresponding structures, materials, acts, and equivalents of all means or step plus function elements in the claims below are intended to include any structure, material, or act for performing the function in combination with other claimed elements as specifically claimed. The description of the present invention has been presented for purposes of illustration and description, but is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the invention. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.

Any combination of one or more computer readable storage device may be utilized. The computer readable storage device may be a computer readable storage medium. The term “computer-readable storage” device does not encompass a signal propagation media. A computer readable storage device may be, for example, but not limited to, an electronic, magnetic, optical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the “C” programming language or similar programming languages. Java is a trademark of Sun Microsystems, Inc. in the United States, other countries, or both. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

Aspects of the present invention are described below with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.

The aspects of the illustrative embodiments provide a data center that operates to respond to power events. The data center responds by adjusting power consumed in response to power events, some of which may be adverse power events. An adverse power event is a signal to reduce electrical power consumption. The signal can be, for example, from an electrical grid operator. Alternatively, the signal can be from a device that operates in response to fluctuations to power consumed or converted by a data center, such as, for example, an air conditioner. Accordingly, the data center may operate under the control of a power cap agent to reduce power consumed by targeted devices and/or software components in the data center following an adverse power event. Similarly, the data center may restore devices and/or software components in response to a positive power event.

FIG. 2 is a block diagram of a data center in accordance with an illustrative embodiment of the invention. A data center is a network of data processing systems that operate at a site to apportion resources among the workloads of one or more customers. Accordingly, network 201 allows multiple data processing centers to communicate with each other, and optionally with additional networks, such as, for example, the Internet. Each data processing system may be, for example, a data processing system such as data processing system 100 of FIG. 1. Each data processing system hardware may form a lowest level of a stack of hardware and software components where successive layers above the hardware level apply greater levels of abstraction to the underlying hardware components.

In the example shown, the data center 200 includes data processing system hardware 210 and data processing system hardware 220. Each data processing system may support one or more logical partitions. A logical partition (LPAR) is an operating system image executing instructions on a data processing system in a manner that permits allocation of excess supporting resources to a parallel or peer operating system image. Operating systems that may be configured to operate in a logical partition include, for example, IBM® z/OS®, IBM® AIX®, Linux®, among others. IBM, z/OS, and AIX are registered trademarks of International Business Machines Corporation in the United States, other countries, or both. Linux® is a registered trademark of Linus Torvalds in the United States, other countries, or both.

LPAR1 211 may rely on an allocation of hardware from data processing system 210. Similarly, LPAR2 221 may rely on allocation of hardware from data processing system hardware 220. It is appreciated that additional data processing systems may be present in data center 200. Moreover, each data processing system may host more than the number of LPARs shown.

Each LPAR supports one or more virtual machines. A virtual machine is a process that executes on a logical partition (LPAR) to perform a function, such as database operations, http service, or any other workload. A virtual machine can be several processes that coordinate together, but are reliant on a single logical partition, or the resources available from a single logical partition. Nevertheless, a virtual machine can cooperate with additional virtual machines to perform, for example, load balancing, where the workload can be shared among several virtual machines. A virtual machine may be instantiated in order to perform any tasks of a workload. Instantiation includes allocating resources reserved by a LPAR to the use of the virtual machine. In contrast, a virtual machine may be shut down. In response to a virtual machine being shut down, any cores that were reserved or shared for use by the virtual machine, may reduce CPU utilization, with an attendant reduction in electrical usage by the one or more cores.

Virtual machines, VM5 213, and VM6 215, are allocated the supporting resources available to LPAR1 211, in this example. Similarly, virtual machines, VM11 223, and VM12 225, are allocated the supporting resources available to LPAR2 221, in this example. Supporting resources are memory, storage, processors and/or processing cores that a LPAR has direct control over by virtue of allocations from a hypervisor. A hypervisor is a software component used to logically partition the hardware into pools of virtualized resources known as logical partitions. A further data processing system may operate to control power usage by data processing hardware of the data center. Data processing system hardware 230 may provide a processor, memory and other data processing system hardware to power cap agent 231. Power cap agent 231 is data processing system instructions executed by the data processing system hardware to command changes in the data center hardware responsive to changing power grid environment. Power cap agent 231 can be, for example, data processing system 100 of FIG. 1. Commands to adjust operating parameters of the data center may be passed via network 201 using known data communication protocols, such as, for example, hypertext transport protocol (HTTP), file transfer protocol (FTP) or secure sockets layer (SSL), among others.

FIG. 3 is a priority record data structure in accordance with an illustrative embodiment of the invention. The priority record data structure 300 is accessed by power cap agent 231 to perform power adjustments in a data center. Initially, the priority record data structure may be input by a data center operator so that each virtual machine has a corresponding power priority. A power priority is an association of a device and/or software component with an order. The order sets the sequence for responsively adjusting the device and/or software component to changing power environment. The software component can be a virtual machine or a logical partition. Changes in the operation of the software component may trigger or be triggered by changes to a supporting resource. A supporting resource is a device that supports a software component. A software component is an LPAR or a virtual partition or processes executing on a data processing system together with associated instructions and data. A power priority virtual machine is a virtual machine that has a corresponding power priority associated with it within a data structure accessible by a power cap agent.

A power priority record is a row in a priority record data structure. For example, a first row in priority record data structure 300 associates virtual machines VM11, and VM12 to power priority 1. Additional associations can describe allowable responses to an adverse power event. For example, virtual machines may be associated with a behavior to allow throttling of the virtual machine. An additional example, virtual machines may be associated with a behavior to allow shutting down of the virtual machines. A throttling is the process of changing one or more clock frequencies or adjusting a voltage to a processor that supports the virtual machine, among other things. The clock frequency is the frequency of the clock signal that gates bits through a processor and/or memory. In addition, throttling can include injecting no-operation machine instructions into a stream of instructions for a processor that supports a virtual machine. A shutting down is the stopping of execution of a process that supports the virtual machine. To shutdown a circuit means that the circuit that supports a virtual machine is either not powered or no clock signal is provided to the circuit. A circuit can be, for example, a processor. If all circuits that support a virtual machine are shut down, then the virtual machine is considered shutdown.

Accordingly, the virtual machines in first power priority row 301 have a higher power priority associated with them as compared to virtual machines in additional rows, such as additional power priority row 311. In additional power priority row 311, virtual machines, VM5 and VM6 are associated with power priority “2”. Power priority “2” is a lower power priority than the power priority “1” of first power priority row 301. Thus, a power cap agent may take actions to reduce power consumption to virtual machines associated with the lower power priority before taking actions with respect to virtual machines associated with a higher power priority. Such actions can be in response to an adverse power event.

FIG. 4 is an additional power priority record data structure in accordance with an illustrative embodiment of the invention. In addition to associating virtual machines with power priorities, the power cap agent may associate logical partitions with power priorities. Accordingly, power priority record data structure 400 may store records that associate a power priority with one or more LPARs. For example, LPAR1 211 of FIG. 2 may be associated with a power priority “1”, the highest priority. Similarly, LPAR2 221 of FIG. 2 may be associated with a power priority “2”, a lower power priority than “1”. Each power priority row can be associated with an allowable behavior. The allowable behavior may be shutting off or may not include shutting off but only throttling. The term “shutting off” means that power is removed to one or more circuits in a data processing system. Shutting off can include disabling a clock signal to a processing core. A shut off logical partition is a logical partition that uses a shut off supporting resource, such as, for example, a processing core. A supporting resource is a resource that is allocated to a logical partition. Accordingly, the supporting resource may used by the logical partition when the resource is not shut off. A throttle limit is the lowest frequency and/or voltage that is applied to one or more circuits that support the LPAR. Such a throttle limit may be a tunable value established when configuring a data processing system.

It is appreciated that the entries in each of priority record data structure 300 and table 400 for allowable behaviors may be stored as binary values to indicate whether a behavior is allowed. For example, the binary value “1” may correspond to “yes” or otherwise indicate allowable for the corresponding field or column of the table. Similarly, the binary value “0” may correspond to a “no” or otherwise indicate that a corresponding field or column of the table is disallowed.

Computer instructions may execute as the power cap agent traverses one or more of priority record data structure 300 or table 400 in response to power events. A description of two processes follows. The first process describes how power adjustments occur in response to adverse power events, as may be indicated by a notice of power cap. The second process describes how power adjustments occur in response to a positive power event, as may be indicated by a notice of relieved power cap. The notice of power cap and the notice of relieved power cap may be transmitted according to any messaging or signaling protocol traversing any conduit or by wireless paths. The notices may include an intervening human element whereby a data center operator confirms the notice through use of a user interface.

FIG. 5 is a flowchart for performing power adjustments in accordance with an illustrative embodiment of the invention. Initially a power cap agent may receive a notice of power cap (step 501). The power cap agent may be power cap agent 231 of FIG. 2. A notice of power cap is an indication from either upstream power producers or downstream power-related devices that an adverse power event has occurred. Upstream and downstream are relative terms that compare devices that are in a chain of power with a data center. An upstream power producer is a producer of electricity for the data center. A downstream power related device can be, for example, an air-conditioner, which handles heat produced as a byproduct of a data center using electricity.

A notice of power cap may identify the data center in a unique manner and specify an allocated power cap requested of the data center. The power cap may be expressed in watts. Alternatively, the power cap may be expressed as a fraction of a previously agreed power level. Accordingly, the power cap can be a data field within a message known as the notice of power cap. Additional information may be passed with the notice of power cap, such as authentication information. The step of receiving a notice of power cap can be one of several steps to establish a power cap. Further steps or substeps can include validating the received notice as well as authenticating the sender. Various steps within the flowchart of FIG. 5 may compare the power cap to power consumption. Power consumption, in this context, is the electrical power consumed by the data processing system. Like the power cap, the power consumption can be expressed in current, for example, watts.

Next, the power cap agent may obtain a lowest power priority record of a virtual machine within the data center specified in the notice for power cap (step 503). The record may be as described in reference to FIG. 3, above.

Next, the power cap agent may determine if a power priority record allows throttling with respect to virtual machines of the record (step 505). If the priority power record allows throttling, the power cap agent may throttle a virtual machine described in the record (step 507). Next, the power cap agent may determine if the power cap is reached (step 509). The power cap determination occurs by summing the power consumed by all parts of the data center. The data center includes those data processing systems that are on a common power grid circuit. In other words, to the extent that data processing systems in multiple buildings are served by the same electrical provider's power grid circuit, those data processing systems may be included within the data center under control of the power cap agent. Power consumption is measured by use of sensors in each data processing system to obtain real-time energy usage information. Accordingly, the data processing system hardware can provide energy use for each data processing system. If the power cap is not reached, the power cap agent may determine if additional virtual machines are referenced in the power priority record (step 511). If there are additional virtual machines so referenced, the power cap agent may obtain the next virtual machine (step 513). Accordingly, the power cap agent may repeat step 507, as well as one or more of the steps 509 and 511 with respect to the next virtual machine.

At some points, the virtual machines for the priority record are exhausted, and the result at step 511 is negative. In response, the power cap agent may determine whether there are additional power priority records (steps 515). The additional records are in relation to the power record data structure that show allowable behaviors associated with lower power priority than the power priority record already traversed. Accordingly, a positive determination to step 515 leads the power cap agent to obtain a next power priority record (step 517). Next, the power cap agent repeats step 505, and if applicable, steps 507, 509, 511, 513, and 515. A negative result to step 505 leads the power cap agent to perform step 511. Step 505 can be arranged, for example, so that additional virtual machines may be targeted for power reduction.

A positive result to step 509 (power cap reached) may cause the power cap agent to terminate processing. A negative result to step 515 (exhausted additional power priority records) may cause the power cap agent to obtain the lowest power priority record of a virtual machine for the data center (step 521). Next, the power cap agent may determine if the power priority record allows shutdown (step 523). If so, the power cap agent may shut down the virtual machine (step 525). In other words, a shutdown of the virtual machine is allowable. Next, the power cap agent may determine if the power cap is reached (step 527). If the power cap is reached, processing may terminate.

On the other hand, the power cap agent may determine that the power cap was not reached. Accordingly, the power cap agent may determine if additional virtual machine is referenced in the power priority record (step 529). If so, the power cap agent may obtain the next virtual machine (step 531). Next, the power cap agent may repeat step 525 with respect to the virtual machine obtained.

A negative result to step 529 may cause the power cap agent to determine if there are additional power priority records (step 533). If so, then the power cap agent may obtain the next power priority record (step 535). Accordingly, the next step for the power cap agent may be step 523. Additional steps 525-535 may be performed one or more times depending on the results at steps 523, 527, 529, and 533. A negative result at step 523 may result in the power cap agent performing step 529 immediately afterward.

A negative result at step 533 may cause the power cap agent to move to a new phase of processing, namely a phase that iterates over one or more LPARs to further reduce power consumption in the data center. Accordingly, the power cap agent may obtain the lowest power priority record for LPARs in a data center (step 541). The power priority record may be selected for example, from table 400, of FIG. 4. Next, the power cap agent may determine if the power priority record allows shut off (step 543). If shut off is allowed, the power cap agent may shut off the LPAR (step 555). The shutting off of an LPAR can include halting all virtual machines that are executing on the LPAR. Next, the power cap agent may determine whether the power cap is reached (step 547). In response to a positive result, the power cap agent may terminate execution.

However, if the power cap is not reached, the power cap agent may determine whether there are additional power priority records for LPARs (step 549). If not, processing may terminate. However, if so, the power cap agent may obtain a next power priority record (step 551). Accordingly, the power cap agent may repeat step 555 as well as one or more subsequent steps 547-551. A negative result at step 543 causes execution to continue at step 549.

It should be noted that the next power priority record, at steps 517 and 535 are for a power priority record that is a next higher priority than the power priority record just processed, and if there is no next higher power priority record, then the next higher priority level after that. For example, if the priority level just traversed is priority level “3”, then the next higher power priority record may be matched to priority level “2”. It is noted that a higher priority level is conventionally denoted by a declining numeral associated with the priority that is higher than the priority level that has a numeral.

The flowchart of FIG. 5 iterates first over allowable throttling for virtual machines over all priorities before iterating over allowable shutting down of virtual machines over all priorities. It is appreciated that an alternative flowchart may first iterate over allowable shutting downs before resorting to traversing the priority table to throttle applicable virtual machines.

The FIG. 5 flowchart begins with receiving a notice of power cap. The notice of power cap may originate from varying sources. One source may be an electrical grid provider. An electrical grid provider is an owner or provider of at least one of a) electricity generation; b) electric power transmission; or c) electricity distribution. The actual signal to suppress the power cap may be generated automatically by monitoring equipment of the electrical grid provider. Alternatively, the notice of power cap may be generated, in part, by a human being who makes a judgment concerning suitable entities to scale back power consumption.

An additional source for a notice of power cap can be a computer room air conditioning (CRAC) unit. A notice of power cap can be a signal from a computer room air conditioning unit. A signal from a computer room air conditioning unit may be a signal transmitted when the computer room air conditioning unit fails in some respect. One source of failure can be a coolant leak. In addition, one or more fans or compressors can fail in the CRAC unit. Accordingly, a change in heat transfer characteristics can be predicted by modeling the failure. Based on the predicted heat transfer change, the signal can be transmitted to adjust the power cap specified in the notice of power cap.

FIG. 6 is a flowchart for relieving power reduction in accordance with an illustrative embodiment of the invention. Flowchart 600 may typically be performed by a power cap agent that controls a data center during a period of adverse power conditions. Initially the power cap agent may receive a notice of relieved power cap (step 601). A notice of relieved power cap, like the notice of power cap, may be received from an upstream device or a downstream device. A notice of relieved power cap is an electronic message that indicates to the power cap agent that a previous notice of power cap is relieved, or at least abated. Accordingly, the notice of relieved power cap may cancel the previously received notice of power cap or otherwise remove any established limit to power consumption of the data center. The notice of relieved power cap may originate from a power providing company. Alternatively, the notice of relieved power cap may originate from a computer room air conditioning unit.

Next, the power cap agent may boot the shut off logical partitions (LPARs) (step 603). The shut off logical partitions may be the logical partitions shut off during one or more steps performed by the power cap agent according to processing of flowchart in FIG. 5. Booting can include applying a clock signal to a processing core. A clock signal may be a waveform designed to trigger operation of sequential logic, such as may be found in a processing core. A processing core can be a microprocessor, arithmetic logic unit or other device that executes machine instructions. Next, the power cap agent may instantiate a plurality of power priority virtual machines (step 605). The power priority virtual machines may be the power priority virtual machines shut down by the power cap agent according to processing of flowchart in FIG. 5.

Next, the power cap agent may restore the virtual machines to unsuppressed power levels (step 607). The unsuppressed power level may be a power level that is not established according to the preferences of the data center owner and/or operator. Processing may terminate thereafter.

The notice of relieved power cap may originate from a computer room air conditioning unit. Alternatively, the notice of relieved power cap may originate from an electrical grid provider.

It should be appreciated that further illustrative embodiments may include, as a sub-step to step 607, a step of restoring a virtual machine in steps that include various gradations of increasing power to a virtual machine. Accordingly, intermediate, partially suppressed power levels can be reached before fully restoring the virtual machines to unsuppressed power levels. Such step-wise power restoration can be used in events where a risk of brownout or blackout has abated, but is not entirely fully brought to zero.

The data center responds to notices of power events by adjusting power consumed in response to power events, some of which may be adverse power events. Accordingly, the data center may operate under the control of a power cap agent to reduce power consumed by targeted devices and/or software components in the data center following an adverse power event. Similarly, the data center may restore devices and/or software components in response to a positive power event. Modest steps may be taken prior to taking action that is more drastic. For example, the power cap agent can progressively throttle higher priority virtual machines before turning off underlying LPARs or the supporting data processing hardware.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The invention can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment containing both hardware and software elements. In a preferred embodiment, the invention is implemented in software, which includes but is not limited to firmware, resident software, microcode, etc.

Furthermore, the invention can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a computer-usable or computer readable medium can be any tangible apparatus that can store the program for use by or in connection with the instruction execution system, apparatus, or device.

The medium can be an electronic, magnetic, optical, or semiconductor system (or apparatus or device). Examples of a computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk-read only memory (CD-ROM), compact disk-read/write (CD-R/W) and DVD.

A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories, which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.

Input/output or I/O devices (including but not limited to keyboards, displays, pointing devices, etc.) can be coupled to the system either directly or through intervening I/O controllers.

Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.

The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiment was chosen and described in order to best explain the principles of the invention, the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims (6)

What is claimed is:
1. A method for managing power consumption in a data center, the method comprising the steps of:
one or more processors receiving a priority record from an operator, the priority record indicating that (a) a first virtual machine has a lower priority than a second virtual machine and can be shut down if the power consumption exceeds a predetermined level, (b) a third virtual machine has a lower priority than the second virtual machine and can be shut down if the power consumption exceeds the predetermined level, and (c) the second virtual machine should not be shut down to conserve power;
one or more processors determining that power consumption in the data center exceeds a predetermined limit, and in response, based on the priority record, reducing power consumption of the first virtual machine, and subsequently,
the one or more processors determining that power consumption in the data center still exceeds the predetermined limit despite the reduced power consumption of the first virtual machine, and in response, based on the priority record, reducing power consumption of the second virtual machine without shutting down the second virtual machine, and subsequently,
the one or more processors determining that power consumption in the data center still exceeds the predetermined limit despite reduced power consumption of the first and second virtual machines, and in response, based on the priority record, reducing power consumption of the third virtual machine, and subsequently,
the one or more processors determining that power consumption in the data center still exceeds the predetermined limit despite the reduction in power consumption of the first, second and third virtual machines, and in response, based on the priority record, shutting down the first virtual machine, and subsequently,
the one or more processors determining that power consumption in the data center still exceeds the predetermined limit despite the shutting down of the first virtual machine and the reduction in power of the second virtual machine, and in response, based on the priority record, shutting down the third virtual machine without shutting down the second virtual machine.
2. The method of claim 1, further comprising:
subsequently to shutting down the first and third virtual machines, receiving, from a computer room air conditioning unit, a cancellation of a reduced predetermined limit, wherein the reduced predetermined limit is a lower limit than the predetermined limit, and in response, restoring power consumption to the first, second and third virtual machines, wherein the step of determining that power consumption in the data center exceeds a predetermined limit further comprises:
setting the predetermined limit; and
receiving, from a computer room air conditioning unit, the reduced predetermined limit, and in response, performing the step of determining that power consumption in the data center exceeds the predetermined limit, and in response, reducing power consumption of the first virtual machine.
3. A computer program product for managing power consumption in a data center, the computer program product comprising a computer readable tangible storage device having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code to receive a priority record from an operator, the priority record indicating that (a) a first virtual machine has a lower priority than a second virtual machine and can be shut down if the power consumption exceeds a predetermined level, (b) a third virtual machine has a lower priority than the second virtual machine and can be shut down if the power consumption exceeds the predetermined level, and (c) the second virtual machine should not be shut down to conserve power;
computer readable program code to determine that power consumption in the data center exceeds a predetermined limit, and in response, based on the priority record, reducing power consumption of the first virtual machine, and subsequently,
computer readable program code to determine that power consumption in the data center still exceeds the predetermined limit despite the reduced power consumption of the first virtual machine, and in response, based on the priority record, reducing power consumption of the second virtual machine without shutting down the second virtual machine, and subsequently,
computer readable program code to determine that power consumption in the data center still exceeds the predetermined limit despite reduced power consumption of the first and second virtual machines, and in response, based on the priority record, reduce power consumption of the third virtual machine, and subsequently,
computer readable program code to determine that power consumption in the data center still exceeds the predetermined limit despite the reduction in power consumption of the first, second and third virtual machines, and in response, based on the priority record, shutting down the first virtual machine, and subsequently,
computer readable program code to determine that the power consumption in the data center still exceeds the predetermined limit despite the shutting down of the first virtual machine and the reduction in power of the second virtual machine, and in response, based on the priority record, shutting down the third virtual machine without shutting down the second virtual machine.
4. The computer program product of claim 3, further comprising:
computer readable program code, subsequent to shutting down the first and third virtual machines, to receive, from a computer room air conditioning unit, a cancellation of a reduced predetermined limit, wherein the reduced predetermined limit is a lower limit than the predetermined limit, and in response, restore power consumption to the first, second and third virtual machines, wherein the computer readable program code to determine that power consumption in the data center exceeds a predetermined limit further comprises:
computer readable program code to set the predetermined limit; and
computer readable program code to receive, from a computer room air conditioning unit, the reduced predetermined limit, and in response, performing the step of determining that power consumption in the data center exceeds the predetermined limit, and in response, reducing power consumption of the first virtual machine.
5. A data processing system for managing power consumption in a data center, the data processing system comprising:
a processor, a computer readable memory and a computer readable tangible storage device;
first program instructions to receive a priority record from an operator, the priority record indicating that (a) a first virtual machine has a lower priority than a second virtual machine and can be shut down if the power consumption exceeds a predetermined level, (b) a third virtual machine has a lower priority than the second virtual machine and can be shut down if the power consumption exceeds the predetermined level, and (c) the second virtual machine should not be shut down to conserve power;
second program instructions to determine that power consumption in the data center exceeds a predetermined limit, and in response, based on the priority record, reducing power consumption of the first virtual machine, and subsequently,
third program instructions to determine that power consumption in the data center still exceeds the predetermined limit despite the reduced power consumption of the first virtual machine, and in response, based on the priority record, reducing power consumption of the second virtual machine without shutting down the second virtual machine, and subsequently,
fourth program instructions to determine that power consumption in the data center still exceeds the predetermined limit despite reduced power consumption of the first and second virtual machines, and in response, based on the priority record, reduce power consumption of the third virtual machine, and subsequently,
fifth program instructions to determine that power consumption in the data center still exceeds the predetermined limit despite the reduction in power consumption of the first, second and third virtual machines, and in response, based on the priority record, shutting down the first virtual machine, and subsequently,
sixth program instructions to determine that the power consumption in the data center still exceeds the predetermined limit despite the shutting down of the first virtual machine and the reduction in power of the second virtual machine, and in response, based on the priority record, shutting down the third virtual machine without shutting down the second virtual machine.
6. The data processing system of claim 5, further comprising:
seventh program instructions to, subsequent to shutting down the first and third virtual machines, to receive, from a computer room air conditioning unit, a cancellation of a reduced predetermined limit, wherein the reduced predetermined limit is a lower limit than the predetermined limit, and in response, restore power consumption to the first, second and third virtual machines, wherein the second program instructions to determine that power consumption in the data center exceeds a predetermined limit, further comprises:
eighth program instructions to set the predetermined limit; and
ninth program instructions to receive, from a computer room air conditioning unit, the reduced predetermined limit, and in response, to perform the first program instructions to determine that power consumption in the data center exceeds the predetermined limit, and in response, based on the priority record, reduce power consumption of the first virtual machine wherein the third program instructions to shut down the first virtual machine are responsive to reducing power consumption of the virtual machine.
US12687241 2010-01-14 2010-01-14 Data center power adjustment Expired - Fee Related US8862922B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US12687241 US8862922B2 (en) 2010-01-14 2010-01-14 Data center power adjustment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US12687241 US8862922B2 (en) 2010-01-14 2010-01-14 Data center power adjustment
US14332809 US9262272B2 (en) 2010-01-14 2014-07-16 Data center power adjustment

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US14332809 Division US9262272B2 (en) 2010-01-14 2014-07-16 Data center power adjustment

Publications (2)

Publication Number Publication Date
US20110173465A1 true US20110173465A1 (en) 2011-07-14
US8862922B2 true US8862922B2 (en) 2014-10-14

Family

ID=44259441

Family Applications (2)

Application Number Title Priority Date Filing Date
US12687241 Expired - Fee Related US8862922B2 (en) 2010-01-14 2010-01-14 Data center power adjustment
US14332809 Active US9262272B2 (en) 2010-01-14 2014-07-16 Data center power adjustment

Family Applications After (1)

Application Number Title Priority Date Filing Date
US14332809 Active US9262272B2 (en) 2010-01-14 2014-07-16 Data center power adjustment

Country Status (1)

Country Link
US (2) US8862922B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9158345B1 (en) * 2012-10-15 2015-10-13 Google Inc. Managing computer performance

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8756441B1 (en) * 2010-09-30 2014-06-17 Emc Corporation Data center energy manager for monitoring power usage in a data storage environment having a power monitor and a monitor module for correlating associative information associated with power consumption
US8849469B2 (en) 2010-10-28 2014-09-30 Microsoft Corporation Data center system that accommodates episodic computation
US9003216B2 (en) * 2011-10-03 2015-04-07 Microsoft Technology Licensing, Llc Power regulation of power grid via datacenter
US9342375B2 (en) 2011-10-26 2016-05-17 Hewlett Packard Enterprise Development Lp Managing workload at a data center
US9318919B2 (en) 2012-06-22 2016-04-19 Microsoft Technology Licensing, Llc Power distribution with wraparound bus
US9369339B2 (en) * 2013-09-30 2016-06-14 Cisco Technology, Inc. Virtual cable modem termination system
WO2015171624A1 (en) * 2014-05-05 2015-11-12 Vigilent Corporation Point-based risk score for managing environmental systems
US9933804B2 (en) 2014-07-11 2018-04-03 Microsoft Technology Licensing, Llc Server installation as a grid condition sensor
CN105760209A (en) * 2014-12-16 2016-07-13 华为技术有限公司 Method and device for removing virtual machines and automatic elastic cluster
FR3031200B1 (en) * 2014-12-30 2017-12-29 Bull Sas Method for automatic management of the electric consumption of a server cluster

Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6202080B1 (en) 1997-12-11 2001-03-13 Nortel Networks Limited Apparatus and method for computer job workload distribution
US6321317B1 (en) 1998-12-16 2001-11-20 Hewlett-Packard Co Apparatus for and method of multi-dimensional constraint optimization in storage system configuration
US20040230848A1 (en) * 2003-05-13 2004-11-18 Mayo Robert N. Power-aware adaptation in a data center
US20050283624A1 (en) * 2004-06-17 2005-12-22 Arvind Kumar Method and an apparatus for managing power consumption of a server
US6985952B2 (en) 2001-10-31 2006-01-10 International Business Machines Corporation Energy-induced process migration
US20060161307A1 (en) * 2005-01-14 2006-07-20 Patel Chandrakant D Workload placement based upon CRAC unit capacity utilizations
US7269751B2 (en) 2003-07-29 2007-09-11 Hewlett-Packard Development Company, L.P. Supplying power to at least one electrical device based on an efficient operating point of a power supply
US7386739B2 (en) 2005-05-03 2008-06-10 International Business Machines Corporation Scheduling processor voltages and frequencies based on performance prediction and power constraints
US20080178029A1 (en) * 2007-01-19 2008-07-24 Microsoft Corporation Using priorities to select power usage for multiple devices
US7421368B2 (en) 2006-12-19 2008-09-02 International Business Machines Corporation Detection of airflow anomalies in electronic equipment
US7461274B2 (en) 2005-08-23 2008-12-02 International Business Machines Corporation Method for maximizing server utilization in a resource constrained environment
US20090037162A1 (en) 2007-07-31 2009-02-05 Gaither Blaine D Datacenter workload migration
US20090132840A1 (en) 2007-11-20 2009-05-21 Vanish Talwar Cross-layer power management in a multi-layer system
US20090164660A1 (en) 2007-12-19 2009-06-25 International Business Machines Corporation Transferring A Logical Partition ('LPAR') Between Two Server Computing Devices Based On LPAR Customer Requirements
US20090168345A1 (en) 2006-06-15 2009-07-02 Martini Valan R Energy saving system and method for cooling computer data center and telecom equipment
US7594128B2 (en) 2004-08-04 2009-09-22 Hewlett-Packard Development Company, L.P. Systems and methods to determine processor utilization
US20090265568A1 (en) 2008-04-21 2009-10-22 Cluster Resources, Inc. System and method for managing energy consumption in a compute environment
US7644051B1 (en) 2006-07-28 2010-01-05 Hewlett-Packard Development Company, L.P. Management of data centers using a model
US20100082290A1 (en) 2008-09-30 2010-04-01 Wood Timothy W Detecting an error in a prediction of resource usage of an application in a virtual environment
US20100161368A1 (en) 2008-12-23 2010-06-24 International Business Machines Corporation Managing energy in a data center
US7844839B2 (en) 2006-12-07 2010-11-30 Juniper Networks, Inc. Distribution of network communications based on server power consumption

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5448716A (en) * 1992-10-30 1995-09-05 International Business Machines Corporation Apparatus and method for booting a multiple processor system having a global/local memory architecture
US7210048B2 (en) * 2003-02-14 2007-04-24 Intel Corporation Enterprise power and thermal management
US7698531B2 (en) * 2007-03-28 2010-04-13 International Business Machines Corporation Workload management in virtualized data processing environment
US8015383B2 (en) * 2007-06-27 2011-09-06 International Business Machines Corporation System, method and program to manage virtual memory allocated by a virtual machine control program
JP2009134565A (en) * 2007-11-30 2009-06-18 Hitachi Ltd Virtual machine system and method for controlling virtual machine system

Patent Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6202080B1 (en) 1997-12-11 2001-03-13 Nortel Networks Limited Apparatus and method for computer job workload distribution
US6321317B1 (en) 1998-12-16 2001-11-20 Hewlett-Packard Co Apparatus for and method of multi-dimensional constraint optimization in storage system configuration
US6985952B2 (en) 2001-10-31 2006-01-10 International Business Machines Corporation Energy-induced process migration
US20040230848A1 (en) * 2003-05-13 2004-11-18 Mayo Robert N. Power-aware adaptation in a data center
US7269751B2 (en) 2003-07-29 2007-09-11 Hewlett-Packard Development Company, L.P. Supplying power to at least one electrical device based on an efficient operating point of a power supply
US20050283624A1 (en) * 2004-06-17 2005-12-22 Arvind Kumar Method and an apparatus for managing power consumption of a server
US7594128B2 (en) 2004-08-04 2009-09-22 Hewlett-Packard Development Company, L.P. Systems and methods to determine processor utilization
US20060161307A1 (en) * 2005-01-14 2006-07-20 Patel Chandrakant D Workload placement based upon CRAC unit capacity utilizations
US7386739B2 (en) 2005-05-03 2008-06-10 International Business Machines Corporation Scheduling processor voltages and frequencies based on performance prediction and power constraints
US7461274B2 (en) 2005-08-23 2008-12-02 International Business Machines Corporation Method for maximizing server utilization in a resource constrained environment
US20090168345A1 (en) 2006-06-15 2009-07-02 Martini Valan R Energy saving system and method for cooling computer data center and telecom equipment
US7644051B1 (en) 2006-07-28 2010-01-05 Hewlett-Packard Development Company, L.P. Management of data centers using a model
US7844839B2 (en) 2006-12-07 2010-11-30 Juniper Networks, Inc. Distribution of network communications based on server power consumption
US7421368B2 (en) 2006-12-19 2008-09-02 International Business Machines Corporation Detection of airflow anomalies in electronic equipment
US20080178029A1 (en) * 2007-01-19 2008-07-24 Microsoft Corporation Using priorities to select power usage for multiple devices
US20090037162A1 (en) 2007-07-31 2009-02-05 Gaither Blaine D Datacenter workload migration
US20090132840A1 (en) 2007-11-20 2009-05-21 Vanish Talwar Cross-layer power management in a multi-layer system
US20090164660A1 (en) 2007-12-19 2009-06-25 International Business Machines Corporation Transferring A Logical Partition ('LPAR') Between Two Server Computing Devices Based On LPAR Customer Requirements
US20090265568A1 (en) 2008-04-21 2009-10-22 Cluster Resources, Inc. System and method for managing energy consumption in a compute environment
US20100082290A1 (en) 2008-09-30 2010-04-01 Wood Timothy W Detecting an error in a prediction of resource usage of an application in a virtual environment
US20100161368A1 (en) 2008-12-23 2010-06-24 International Business Machines Corporation Managing energy in a data center

Non-Patent Citations (17)

* Cited by examiner, † Cited by third party
Title
Akers, Jason B; Response to Office Action; U.S. Appl. No. 12/627,765; May 1, 2012; USPTO.
Connolly, Mark A; Office Action; U.S. Appl. No. 12/627,765; Feb. 1, 2012; USPTO.
Coskun, A.K.; Proactive Temperature Balancing for Low Cost Thermal Management in MPSoCs; Item: Article; Date: May 2008; IEEE.
Coskun, A.K.; Temperature Management in Multiprocessor SoCs Using Online Learning; Item: Article; Date: Jun. 2008; ACM; 2008, Anaheim, CA, USA.
Das, R.; Autonomic Multi-Agent Management of Power and Performance in Data Centers; Item: Article; Date: May 2008; International Foundation for Autonomous Agents and Multiagent Systems; http://www.ifaamas.org.
Eberle, H.; High-Radix Crossbar Switches Enabled by Proximity Communication; Item: Article; Date: Nov. 2008; IEEE.
Gerow, J.; Power Supply Efficiency; Item; Article; Date: Jun. 26, 2006; Motherboards.org; http://www.motherboards.org/articles/guides/1487-7.html.
Gerow, J.; Power Supply Efficiency; Item; Article; Date: Jun. 26, 2006; Motherboards.org; http://www.motherboards.org/articles/guides/1487—7.html.
IBM; IBM BladeCenter JS22 Express Blade; Item: Whitepaper; Date: Oct. 2008; IBM Corporation; Somers, NY, USA.
IBM; IBM EnergyScale for POWER6 Processor-Based Systems; Item: Whitepaper; Date: Oct. 2009; IBM Corporation; Somers, NY, USA.
IBM; IBM Power 550 Express Server; Item: Whitepaper; Date: Apr. 2009; IBM Corporation; Somers, NY, USA.
IBM; Optimizing the Energy Consumption of a Group of Servers; Item: Article; Date: Apr. 8, 2008; IP.com.
Khan, O.; A Framework for Predictive Dynamic Temperature Management of Microprocessor Systems; Item: Article; Date: May 2008; IEEE; Department of Electrical and Computer Engineering, University of Massachusetts Amherst, Amherst, MA, USA.
Kusic, D.; Power and Performance Management of Virtualized Computing Environments Via Lookahead Control; Item: Article; Date: May 2008; IEEE.
Shu, J.; Policy of File Migration at Server in Cluster File System; Item: Article-2004 IEEE International Symposium on Cluster Computing and the Grid; Date: 2004; IEEE; Computer Science and Technology Department, Tsinghua University, Beijing, P.R. China.
Shu, J.; Policy of File Migration at Server in Cluster File System; Item: Article—2004 IEEE International Symposium on Cluster Computing and the Grid; Date: 2004; IEEE; Computer Science and Technology Department, Tsinghua University, Beijing, P.R. China.
Weddle, C.; PARAID: A Gear-Shifting Power-Aware Raid; Item: Articlel3, vol. 3, No. 3 Date: Oct. 2007; ACM.

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9158345B1 (en) * 2012-10-15 2015-10-13 Google Inc. Managing computer performance

Also Published As

Publication number Publication date Type
US20140331039A1 (en) 2014-11-06 application
US9262272B2 (en) 2016-02-16 grant
US20110173465A1 (en) 2011-07-14 application

Similar Documents

Publication Publication Date Title
Li et al. Enacloud: An energy-saving application live placement approach for cloud computing environments
Hameed et al. A survey and taxonomy on energy efficient resource allocation techniques for cloud computing systems
Kim et al. Power-aware provisioning of cloud resources for real-time services
Nathuji et al. VPM tokens: virtual machine-aware power budgeting in datacenters
US20120030356A1 (en) Maximizing efficiency in a cloud computing environment
US20140019966A1 (en) System and method for continuous optimization of computing systems with automated assignment of virtual machines and physical machines to hosts
Beloglazov et al. Energy efficient resource management in virtualized cloud data centers
US20130318371A1 (en) Systems and methods for dynamic power allocation in an information handling system environment
US20120284408A1 (en) Workload-aware placement in private heterogeneous clouds
Sakellari et al. A survey of mathematical models, simulation approaches and testbeds used for research in cloud computing
US20100174928A1 (en) Optimizer Mechanism to Increase Battery Length for Mobile Devices
US8185894B1 (en) Training a virtual machine placement controller
US20100185882A1 (en) Computer System Power Management Based on Task Criticality
US20110271283A1 (en) Energy-aware job scheduling for cluster environments
US20130191527A1 (en) Dynamically building a set of compute nodes to host the user's workload
US20120116599A1 (en) Allocation of Energy Budgets to Individual Partitions
Zhu et al. Real-time tasks oriented energy-aware scheduling in virtualized clouds
US20090199193A1 (en) System and method for managing a hybrid compute environment
US20100070784A1 (en) Reducing Power Consumption in a Server Cluster
US20120144219A1 (en) Method of Making Power Saving Recommendations in a Server Pool
US8341626B1 (en) Migration of a virtual machine in response to regional environment effects
Strunk et al. Does live migration of virtual machines cost energy?
Do et al. ptop: A process-level power profiling tool
US20120096293A1 (en) Directed Resource Folding for Power Management
US20110161696A1 (en) Reducing energy consumption in a cloud computing environment

Legal Events

Date Code Title Description
AS Assignment

Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:AKERS, JASON B.;CLAY, ROSS B.;JONES, PERRY L.;AND OTHERS;SIGNING DATES FROM 20100108 TO 20100112;REEL/FRAME:023782/0502

FEPP

Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.)

LAPS Lapse for failure to pay maintenance fees

Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY